%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2016/08.22.13.41
%2 sid.inpe.br/sibgrapi/2016/08.22.13.41.09
%T 3DRT – Sistema Embarcado para Reconstrução 3D em Tempo Real
%D 2016
%A Fernandez, Luiz E. O.,
%A Avila, Elizabeth V. C.,
%A Goncalves, Luiz M. G.,
%@affiliation Universidade Federal do Rio Grande do Norte
%@affiliation Universidade Federal do Rio Grande do Norte
%@affiliation Universidade Federal do Rio Grande do Norte
%E Aliaga, Daniel G.,
%E Davis, Larry S.,
%E Farias, Ricardo C.,
%E Fernandes, Leandro A. F.,
%E Gibson, Stuart J.,
%E Giraldi, Gilson A.,
%E Gois, João Paulo,
%E Maciel, Anderson,
%E Menotti, David,
%E Miranda, Paulo A. V.,
%E Musse, Soraia,
%E Namikawa, Laercio,
%E Pamplona, Mauricio,
%E Papa, João Paulo,
%E Santos, Jefersson dos,
%E Schwartz, William Robson,
%E Thomaz, Carlos E.,
%B Conference on Graphics, Patterns and Images, 29 (SIBGRAPI)
%C São José dos Campos, SP, Brazil
%8 4-7 Oct. 2016
%I Sociedade Brasileira de Computação
%J Porto Alegre
%S Proceedings
%K real-time vision, 3D reconstruction, point cloud.
%X We present current efforts towards the development of an embedded system for 3D reconstruction of a scene in real time. Algorithms for system calibration, rectification, and 3D reconstruction of a point cloud using the NVIDIA Jetson TK1 based on a stereo disparity map given by the Stereolabs ZED 3D camera are currently developed. They are implemented using the stereo camera SDK, in C++, and the FreeGLUT library. We have built a tool for visualization of the reconstructed data in a monitor and, as a partial contribution of this work, we have done an analysis to measure time processing for each step of the whole process to certify that the real-time requirement is met. Partial results indicate feasibility of a more complex, efficient system (with precision and real-time operation) thus allowing its use in robotics vision applications.
%@language pt
%3 3D_RT (10).pdf